Skillv1.0.0

ClawScan security

Social Media Optimizer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 2, 2026, 12:41 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only skill that provides platform-specific social media optimization advice and its requirements and instructions are consistent with that purpose.
Guidance: This skill is low-risk and internally consistent: it only contains advice and templates for optimizing content across platforms. Before installing, consider that (1) the source/homepage is unknown — prefer skills from known authors if you need stronger trust guarantees, (2) outputs are recommendations only and should be reviewed for compliance with each platform's rules and your brand voice, and (3) test suggestions on non-critical accounts first. Because it asks for no credentials or installs, there is minimal technical risk, but avoid pasting any private tokens or account credentials into prompts when using it.

Purpose & Capability: okName and description match the SKILL.md content: a guidance-oriented social media optimization assistant for Chinese platforms. No binaries, installs, or credentials are requested that would be unrelated to giving advice.
Instruction Scope: okSKILL.md contains only prescriptive guidance, templates, scoring rubrics, and output formatting. It does not instruct the agent to read local files, access environment variables, call external endpoints, or exfiltrate data.
Install Mechanism: okNo install spec and no code files — the skill is instruction-only, so nothing is written to disk or added to the runtime beyond the prompt text itself.
Credentials: okThe skill requires no environment variables, credentials, or config paths. There are no requests for unrelated secrets or platform credentials.
Persistence & Privilege: okalways is false and default agent invocation settings apply. The skill does not request elevated persistence or modification of other skills or system settings.